Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts related to disappearance or vanishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rong
    -0.16
     awake
    -0.15
     تÙĤÙĪ
    -0.15
    ãĤ¤ãĥ«
    -0.15
     оÑī
    -0.15
    immel
    -0.15
    åŀ
    -0.14
     вб
    -0.14
    éĻµ
    -0.14
    VICE
    -0.14
    POSITIVE LOGITS
     leaving
    0.26
     never
    0.22
     forever
    0.21
     into
    0.21
     gone
    0.21
     Never
    0.20
     disappear
    0.20
     leave
    0.19
     Gone
    0.19
     Leaving
    0.18
    Act Density 0.173%

    No Known Activations